Hex dump: Difference between revisions
Add JavaScript
(Add JavaScript) |
|||
| (8 intermediate revisions by 5 users not shown) | |||
Line 13:
For example, the string "Rosetta Code is a programming chrestomathy site 😀." encoded in [[wp:UTF-16|UTF-16]] (little-endian - the first two bytes are the [[wp:Byte_order_mark|byte order mark]]), displayed in the canonical format is:
<syntaxhighlight lang="hexdump">
00000000 ff fe 52 00 6f 00 73 00 65 00 74 00 74 00 61 00 |..R.o.s.e.t.t.a.|
00000010 20 00 43 00 6f 00 64 00 65 00 20 00 69 00 73 00 | .C.o.d.e. .i.s.|
Line 22:
00000060 20 00 3d d8 00 de 2e 00 | .=.....|
00000068
</syntaxhighlight>
;Task
Line 40:
Implement a binary mode. For this task, in binary mode, the example above should be displayed like this:
<syntaxhighlight lang="hexdump">
00000000 11111111 11111110 01010010 00000000 01101111 00000000 |..R.o.|
00000006 01110011 00000000 01100101 00000000 01110100 00000000 |s.e.t.|
Line 60:
00000066 00101110 00000000 |..|
00000068
</syntaxhighlight>
Other hexdump/xxd features and a command line interface to your program are optional.
Line 485:
00000066 00101110 00000000 |..|
0000006c
</pre>
=={{header|JavaScript}}==
<syntaxhighlight lang="javascript">
// Generate UTF-16 LE bytes from a string.
function* utf16leBytes(str) {
// Little endian byte order mark.
yield 0xff;
yield 0xfe;
// Iterate code units.
let code_unit;
for (let i = 0; i < str.length; i++) {
code_unit = str.charCodeAt(i);
yield code_unit & 0xff;
yield code_unit >>> 8;
}
}
/**
* Generate sequences of length {@link n} from items in iterable {@link it}.
*/
function* groupBy(it, n) {
let chunk = [];
for (const item of it) {
chunk.push(item);
if (chunk.length == n) {
yield chunk;
chunk = [];
}
}
if (chunk.length) {
yield chunk;
}
}
/**
* @callback Formatter
* @param {Array<number>} chunk
* @returns {string} {@link chunk} formatted for output on one line.
*/
function canonicalFormatter(chunk) {
const bytesAsHex = chunk.map((byte) => byte.toString(16).padStart(2, "0"));
const hex = `${bytesAsHex.slice(0, 8).join(" ")} ${bytesAsHex
.slice(8)
.join(" ")}`.padEnd(48, " ");
const ascii = chunk
.map((byte) => (byte > 31 && byte < 127 ? String.fromCharCode(byte) : "."))
.join("");
return `${hex} |${ascii}|`;
}
/**
* @callback Formatter
* @param {Array<number>} chunk
* @returns {string} {@link chunk} formatted for output on one line.
*/
function binaryFormatter(chunk) {
const bits = chunk
.map((byte) => byte.toString(2).padStart(8, "0"))
.join(" ")
.padEnd(53, " ");
const ascii = chunk
.map((byte) => (byte > 31 && byte < 127 ? String.fromCharCode(byte) : "."))
.join("");
return `${bits} |${ascii}|`;
}
/**
* Generate a textual representation of bytes in {@link data} one line at a time.
*
* @param {Iterable<number>} data
* @param {number} skip
* @param {number} length
* @param {Formatter} formatter
* @param {number} chunkSize
*/
function* hexDumpLines(
data,
skip = 0,
length = Infinity,
formatter = canonicalFormatter,
chunkSize = 16
) {
const it = data[Symbol.iterator]();
for (let i = 0; i < skip; i++) {
it.next();
}
let offset = skip;
let byteCount = 0;
let line = "";
for (let chunk of groupBy(data, chunkSize)) {
// Discard excess bytes if we've overshot length.
if (byteCount + chunk.length > length) {
chunk = chunk.slice(0, length - byteCount);
}
line = formatter(chunk);
yield `${offset.toString(16).padStart(8, "0")} ${line}`;
offset += chunkSize;
byteCount += chunk.length;
if (byteCount >= length) {
break;
}
}
// Final byte count
yield (byteCount + skip).toString(16).padStart(8, "0");
}
/**
* Log a hex dump of {@link data} to the console.
*
* @param {Iterable<number>} data
* @param {number} skip
* @param {number} length
* @param {Formatter} formatter
* @param {number} chunkSize
*/
function consoleHexDump(
data,
skip = 0,
length = Infinity,
formatter = canonicalFormatter,
chunkSize = 16
) {
for (const line of hexDumpLines(data, skip, length, formatter, chunkSize)) {
console.log(line);
}
}
const exampleData = "Rosetta Code is a programming chrestomathy site 😀.";
consoleHexDump(utf16leBytes(exampleData));
console.log("");
consoleHexDump(utf16leBytes(exampleData), 20, 25);
console.log("");
consoleHexDump(utf16leBytes(exampleData), 0, Infinity, binaryFormatter, 6);
</syntaxhighlight>
{{out}}
<pre>
00000000 ff fe 52 00 6f 00 73 00 65 00 74 00 74 00 61 00 |..R.o.s.e.t.t.a.|
00000010 20 00 43 00 6f 00 64 00 65 00 20 00 69 00 73 00 | .C.o.d.e. .i.s.|
00000020 20 00 61 00 20 00 70 00 72 00 6f 00 67 00 72 00 | .a. .p.r.o.g.r.|
00000030 61 00 6d 00 6d 00 69 00 6e 00 67 00 20 00 63 00 |a.m.m.i.n.g. .c.|
00000040 68 00 72 00 65 00 73 00 74 00 6f 00 6d 00 61 00 |h.r.e.s.t.o.m.a.|
00000050 74 00 68 00 79 00 20 00 73 00 69 00 74 00 65 00 |t.h.y. .s.i.t.e.|
00000060 20 00 3d d8 00 de 2e 00 | .=.....|
00000068
00000014 6f 00 64 00 65 00 20 00 69 00 73 00 20 00 61 00 |o.d.e. .i.s. .a.|
00000024 20 00 70 00 72 00 6f 00 67 | .p.r.o.g|
0000002d
00000000 11111111 11111110 01010010 00000000 01101111 00000000 |..R.o.|
00000006 01110011 00000000 01100101 00000000 01110100 00000000 |s.e.t.|
0000000c 01110100 00000000 01100001 00000000 00100000 00000000 |t.a. .|
00000012 01000011 00000000 01101111 00000000 01100100 00000000 |C.o.d.|
00000018 01100101 00000000 00100000 00000000 01101001 00000000 |e. .i.|
0000001e 01110011 00000000 00100000 00000000 01100001 00000000 |s. .a.|
00000024 00100000 00000000 01110000 00000000 01110010 00000000 | .p.r.|
0000002a 01101111 00000000 01100111 00000000 01110010 00000000 |o.g.r.|
00000030 01100001 00000000 01101101 00000000 01101101 00000000 |a.m.m.|
00000036 01101001 00000000 01101110 00000000 01100111 00000000 |i.n.g.|
0000003c 00100000 00000000 01100011 00000000 01101000 00000000 | .c.h.|
00000042 01110010 00000000 01100101 00000000 01110011 00000000 |r.e.s.|
00000048 01110100 00000000 01101111 00000000 01101101 00000000 |t.o.m.|
0000004e 01100001 00000000 01110100 00000000 01101000 00000000 |a.t.h.|
00000054 01111001 00000000 00100000 00000000 01110011 00000000 |y. .s.|
0000005a 01101001 00000000 01110100 00000000 01100101 00000000 |i.t.e.|
00000060 00100000 00000000 00111101 11011000 00000000 11011110 | .=...|
00000066 00101110 00000000 |..|
00000068
</pre>
Line 594 ⟶ 777:
=={{header|Phix}}==
<!--
<syntaxhighlight lang="phix">
with javascript_semantics
sequence utf16 = #FEFF & "Rosetta Code is a programming chrestomathy site " & {#d83d,#DE00,'.'}
function to2(integer i) return {and_bits(i,#FF),floor(i/#100)} end function
constant string s = flatten(apply(utf16,to2),"")
--or: (javascript incompatible)
--constant string s = get_text(filename) -- (if you have a suitable premade one to hand)
procedure hexdump(string s, integer start=0, finish=-1, bool bHex=true, bFinalSize=true)
s = s[start+1..finish]
integer ll = iff(bHex?16:6), ls = length(s)
string hbfmt = iff(bHex?"%02x ":"%08b "),
lnfmt = "%08x %s |%-" & sprintf("%d",ll) & "s|\n"
sequence lines = split_by(s,ll)
for l in lines do
string hb = " ", ascii = ""
for i,b in l do
hb &= sprintf(hbfmt,b)
if b<' ' or b>'~' then b = '.' end if
ascii &= b
if i=8 then hb &= ' ' end if
end for
hb = pad_tail(hb,iff(bHex?50:55))
printf(1,lnfmt,{start,hb,ascii})
start += length(l)
end for
if bFinalSize then
printf(1,"%08x\n",{ls})
end if
end procedure
printf(1,"Hexadecimal:\n")
hexdump(s)
printf(1,"\nBinary:\n")
hexdump(s,bHex:=false)
</syntaxhighlight>
Although not shown, the intention is the outer calling code (last four lines) could call hexdump() to display one page at a time, with appropriate user input, and/or read s in chunks and pass a file offset instead of or as well as start, finish.
{{out}}
Line 873 ⟶ 1,057:
00000068
</pre>
=={{header|Raku}}==
The hexdump() routine expects a Blob. How you feed it the Blob is up to you. You may read a file in binary mode, encode a string, whatever. Using encoded strings here for a compact, self-contained example. Encoded in a few different ways for variety.
<syntaxhighlight lang="raku" line>say my $string = 'Rosettacode is a programming crestomathy site 😀. 🍨 👨👩👦 ⚽ ¯\_(ツ)_/¯';
say "\nHex dump UTF-16BE, offset 0";
hexdump $string.encode("UTF-16BE");
say "\nHex dump UTF-16LE, offset 0";
hexdump $string.encode("UTF-16LE");
say "\nBinary dump UTF-8, offset 17";
hexdump $string.encode("UTF-8"), :bin, :17offset;
sub hexdump(Blob $blob, Int :$offset is copy = 0, :$bin = False) {
my ($fmt, $space, $batch) = $bin ?? ("%08b", ' ' x 8, 6) !! ("%02X", ' ', 16);
for $blob.skip($offset).batch($batch) {
my @h = flat $_».fmt($fmt), $space xx $batch;
@h[7] ~= ' ';
printf "%08X %s |%s|\n", $offset, @h[^$batch].Str,
$_».chr.join.subst(/<-print>|\t|\n/, '.', :g);
$offset += $batch;
}
}</syntaxhighlight>
{{out}}
<pre>Rosettacode is a programming crestomathy site 😀. 🍨 👨👩👦 ⚽ ¯\_(ツ)_/¯
Hex dump UTF-16BE, offset 0
00000000 00 52 00 6F 00 73 00 65 00 74 00 74 00 61 00 63 |.R.o.s.e.t.t.a.c|
00000010 00 6F 00 64 00 65 00 20 00 69 00 73 00 20 00 61 |.o.d.e. .i.s. .a|
00000020 00 20 00 70 00 72 00 6F 00 67 00 72 00 61 00 6D |. .p.r.o.g.r.a.m|
00000030 00 6D 00 69 00 6E 00 67 00 20 00 63 00 72 00 65 |.m.i.n.g. .c.r.e|
00000040 00 73 00 74 00 6F 00 6D 00 61 00 74 00 68 00 79 |.s.t.o.m.a.t.h.y|
00000050 00 20 00 73 00 69 00 74 00 65 00 20 D8 3D DE 00 |. .s.i.t.e. Ø=Þ.|
00000060 00 2E 00 20 00 20 00 20 00 20 D8 3C DF 68 00 20 |... . . . Ø<ßh. |
00000070 D8 3D DC 68 20 0D D8 3D DC 69 20 0D D8 3D DC 66 |Ø=Üh .Ø=Üi .Ø=Üf|
00000080 00 20 26 BD 00 20 00 AF 00 5C 00 5F 00 28 30 C4 |. &½. .¯.\._.(0Ä|
00000090 00 29 00 5F 00 2F 00 AF |.)._./.¯|
Hex dump UTF-16LE, offset 0
00000000 52 00 6F 00 73 00 65 00 74 00 74 00 61 00 63 00 |R.o.s.e.t.t.a.c.|
00000010 6F 00 64 00 65 00 20 00 69 00 73 00 20 00 61 00 |o.d.e. .i.s. .a.|
00000020 20 00 70 00 72 00 6F 00 67 00 72 00 61 00 6D 00 | .p.r.o.g.r.a.m.|
00000030 6D 00 69 00 6E 00 67 00 20 00 63 00 72 00 65 00 |m.i.n.g. .c.r.e.|
00000040 73 00 74 00 6F 00 6D 00 61 00 74 00 68 00 79 00 |s.t.o.m.a.t.h.y.|
00000050 20 00 73 00 69 00 74 00 65 00 20 00 3D D8 00 DE | .s.i.t.e. .=Ø.Þ|
00000060 2E 00 20 00 20 00 20 00 20 00 3C D8 68 DF 20 00 |.. . . . .<Øhß .|
00000070 3D D8 68 DC 0D 20 3D D8 69 DC 0D 20 3D D8 66 DC |=ØhÜ. =ØiÜ. =ØfÜ|
00000080 20 00 BD 26 20 00 AF 00 5C 00 5F 00 28 00 C4 30 | .½& .¯.\._.(.Ä0|
00000090 29 00 5F 00 2F 00 AF 00 |)._./.¯.|
Binary dump UTF-8, offset 17
00000011 01110000 01110010 01101111 01100111 01110010 01100001 |progra|
00000017 01101101 01101101 01101001 01101110 01100111 00100000 |mming |
0000001D 01100011 01110010 01100101 01110011 01110100 01101111 |cresto|
00000023 01101101 01100001 01110100 01101000 01111001 00100000 |mathy |
00000029 01110011 01101001 01110100 01100101 00100000 11110000 |site ð|
0000002F 10011111 10011000 10000000 00101110 00100000 00100000 |.... |
00000035 00100000 00100000 11110000 10011111 10001101 10101000 | ð..¨|
0000003B 00100000 11110000 10011111 10010001 10101000 11100010 | ð..¨â|
00000041 10000000 10001101 11110000 10011111 10010001 10101001 |..ð..©|
00000047 11100010 10000000 10001101 11110000 10011111 10010001 |â..ð..|
0000004D 10100110 00100000 11100010 10011010 10111101 00100000 |¦ â.½ |
00000053 11000010 10101111 01011100 01011111 00101000 11100011 |¯\_(ã|
00000059 10000011 10000100 00101001 01011111 00101111 11000010 |..)_/Â|
0000005F 10101111 |¯|</pre>
=={{header|Wren}}==
Line 880 ⟶ 1,131:
As my text editor always adds a trailing \n, the method removes this before dumping the remainder.
<syntaxhighlight lang="
import "./seq" for Lst
import "./fmt" for Fmt
Line 928 ⟶ 1,179:
}
}
var text = "|" + ascii.join(
var offset = start + i * rl
if (i < rc-1 || lc == rl) {
Line 967 ⟶ 1,218:
00000040 68 00 72 00 65 00 73 00 74 00 6f 00 6d 00 61 00 |h.r.e.s.t.o.m.a.|
00000050 74 00 68 00 79 00 20 00 73 00 69 00 74 00 65 00 |t.h.y. .s.i.t.e.|
00000060 20 00 3d d8 00 de 2e 00 | .=.....
00000068
Line 981 ⟶ 1,232:
00000050 116 000 104 000 121 000 032 000 115 000 |t.h.y. .s.|
0000005a 105 000 116 000 101 000 032 000 061 216 |i.t.e. .=.|
00000064 000 222 046 000 |....
00000068
Line 995 ⟶ 1,246:
00000050 164 000 150 000 171 000 040 000 163 000 |t.h.y. .s.|
0000005a 151 000 164 000 145 000 040 000 075 330 |i.t.e. .=.|
00000064 000 336 056 000 |....
00000068
Line 1,032 ⟶ 1,283:
0000005a 01101001 00000000 01110100 00000000 01100101 00000000 |i.t.e.|
00000060 00100000 00000000 00111101 11011000 00000000 11011110 | .=...|
00000066 00101110 00000000 |..
00000068
Dump of "example_utf16.txt" in base 16 from byte index 2 to 25:
00000002 52 00 6f 00 73 00 65 00 74 00 74 00 61 00 20 00 |R.o.s.e.t.t.a. .|
00000012 43 00 6f 00 64 00 65 00 |C.o.d.e.
0000001a
</pre>
=={{header|XPL0}}==
Works for both MS-DOS and RPi Linux.
<syntaxhighlight lang "XPL0">int Offset, Length, Limit, Byte;
char FileName(80);
func GetByte; \Return a byte from input file
int Return;
[Return:= Byte;
Byte:= ChIn(3); \one-byte look-ahead detects EOF
return Return;
];
proc DumpHex(I); \Show line of hex and its ASCII, starting at offset I
int I, J;
char Line(16);
[HexOut(0, I); Text(0, " ");
SetHexDigits(2);
for J:= 0 to 15 do
[Line(J):= GetByte;
if GetErr and I+J < Limit then Limit:= I+J;
if I+J < Limit then
HexOut(0, Line(J))
else Text(0, " ");
ChOut(0, ^ );
if (J&7) = 7 then ChOut(0, ^ );
];
SetHexDigits(8); \restore default number of digits
ChOut(0, ^|); \display corresponding ASCII characters
for J:= 0 to 15 do
if I+J < Limit then
ChOut(0, if Line(J)<=$1F or Line(J)>=$7F then ^. else Line(J));
ChOut(0, ^|); CrLf(0);
];
func OpenInFile; \Open file for input; return 'true' if success
int FD; \file descriptor
[FD:= FOpen(FileName, 0);
FSet(FD, ^i); \associate device 3 with file; use small buffer (i)
OpenI(3);
return GetErr = 0;
];
func GetFileName; \Get FileName from command line, and set any switches
int C, I; \returns 'true' if no errors
[FileName(0):= 0;
C:= ChIn(8);
loop [while C = $20 do C:= ChIn(8); \skip leading spaces (for MS-DOS)
if C = ^- then
[case ChIn(8) of
^s: Offset:= IntIn(8);
^n: Length:= IntIn(8)
other return false; \Error
Backup; \in case number was terminated by CR or EOF
C:= ChIn(8);
]
else if C = $0D\CR\ or C = $1A\EOF\ then quit
else [I:= 0;
repeat FileName(I):= C;
I:= I+1;
C:= ChIn(8);
until C <= $20;
FileName(I):= 0; \terminate string
];
];
return true;
];
int I;
[Trap(false); \don't abort program on errors
Offset:= 0; Length:= -1>>1;
if not GetFileName then
[Text(0, "Unrecognized switch. Use -s offset, -n length"); exit];
if not OpenInFile(FileName) then
[Text(0, "File not found"); exit];
Byte:= ChIn(3); \look ahead
Limit:= Offset + Length;
if Limit < 0 then Limit:= -1>>1;
for I:= 0 to Offset-1 do \skip any offset bytes
[GetByte; if GetErr then exit];
repeat DumpHex(I);
I:= I + 16;
until I >= Limit;
HexOut(0, Limit); CrLf(0);
]</syntaxhighlight>
{{out}}
<pre>
hexdump examp16.txt
00000000 FF FE 52 00 6F 00 73 00 65 00 74 00 74 00 61 00 |..R.o.s.e.t.t.a.|
00000010 20 00 43 00 6F 00 64 00 65 00 20 00 69 00 73 00 | .C.o.d.e. .i.s.|
00000020 20 00 61 00 20 00 70 00 72 00 6F 00 67 00 72 00 | .a. .p.r.o.g.r.|
00000030 61 00 6D 00 6D 00 69 00 6E 00 67 00 20 00 63 00 |a.m.m.i.n.g. .c.|
00000040 68 00 72 00 65 00 73 00 74 00 6F 00 6D 00 61 00 |h.r.e.s.t.o.m.a.|
00000050 74 00 68 00 79 00 20 00 73 00 69 00 74 00 65 00 |t.h.y. .s.i.t.e.|
00000060 20 00 3D D8 00 DE 2E 00 | .=.....|
00000068
hexdump -s 20 examp16.txt -n 20
00000014 6F 00 64 00 65 00 20 00 69 00 73 00 20 00 61 00 |o.d.e. .i.s. .a.|
00000024 20 00 70 00 | .p.|
00000028
</pre>
| |||